Hello,
thanks for your reply.
Jeff Squyres wrote:
Try running with:
mpirun.openmpi-1.4.1 --mca btl_base_verbose 50 --mca btl self,openib -n 2
--mca btl_openib_verbose 100 ./IMB-MPI1 -npmin 2 PingPong
the output is exactly the same as before.
Also, are you saying that running the same co
Ok, we've entered the Land of Really Weird - I've never seen a btl work with
one mpi app and not another.
Some q's:
- are you running both apps on the same nodes?
- is anything else running on the nodes at the same time (e.g., other mpi jobs
using openfabrics)?
- is the imb compiled for ompi 1.
Am 18.05.2010 15:46, schrieb Ralph Castain:
Hello,
> Starting in the 1.3 series, you have to tell OMPI where to find the
> default hostfile. So put this in your default MCA param file:
>
> orte_default_hostfile=
>
> That should fix it.
>
yes it fix it.
Thanks,
Stefan Kuhne
signature.asc
De
Hi,
Jeff Squyres (jsquyres) wrote:
Ok, we've entered the Land of Really Weird - I've never seen a btl work with
one mpi app and not another.
Some q's:
- are you running both apps on the same nodes?
yes, in fact I'm running them in the same interactive Job.
- is anything else running on th
Dear list,
One of our users faces problems running his application (large CP2K cases)
Cluster:
OpenMPI 1.4.2, SLES 9, gcc 4.1.2, OFED 1.4 on Intel Nehalem (5350)
The message is:
[[45776,1],214][btl_openib_component.c:2951:handle_wc] from node140 to:
node400 error polling LP CQ with status LOCAL
On May 19, 2010, at 7:18 AM, Peter Kruse wrote:
> > - are you running both apps on the same nodes?
>
> yes, in fact I'm running them in the same interactive Job.
This is truly freaky; I've seen the same thing on Peter's computer.
We're working the issue off-list; we'll post the solution when we
Hello,
Thank for the advice, it works with NFS !
But :
1) it doesn't work anymore, if I remove --prefix /Network/opt/openmpi-1.4.2 (is
there a way to remove it on OSX, already declared ?)
2) I must use the option -static-intel at link else i have a problem with
libiomp5.dylib not found
Chri
Dear all,
I use the following code:
#include "stdlib.h"
#include "stdio.h"
#include "mpi.h"
#include "math.h"
#include "unistd.h" /* sleep */
int my_num, mpi_size ;
int
main(int argc, char *argv[])
{
MPI_Init(&argc, &argv) ;
MPI_Comm_rank(MPI_COMM_WORLD, &my_num);
MPI_Comm_size(MPI_COMM_
On May 19, 2010, at 5:12 AM, Christophe Peyret wrote:
> 1) it doesn't work anymore, if I remove --prefix /Network/opt/openmpi-1.4.2
> (is there a way to remove it on OSX, already declared ?)
I'm assuming you're referring to shared libraries and/or executables not being
found if you don't speci
Hello,
I would like to build OMPI V1.4.2 and make it available to our users at the
Supercomputing Center at TAMU. Our system is a 2-socket, 4-core Nehalem
@2.8GHz, 24GiB DRAM / node, 324 nodes connected to 4xQDR Voltaire fabric,
CentOS/RHEL 5.4.
I have been trying to find the following informa
Hi,
I am trying to use intercommunicator ::Allgather between two child process.
I have fortran and Python code,
I am using mpi4py for python. It seems that ::Allgather is not working
properly in my desktop.
I have contacted first mpi4py developers (Lisandro Dalcin), he simplified
my problem and
Hi,
I am wondering if there is a way to run a particular process among multiple
processes on the console of a linux cluster.
I want to see the screen output (standard output) of a particular process
(using a particular ID of a process) on the console screen while the MPI
program is running. I
12 matches
Mail list logo
